US11372087B2 - Radar system and method for receiving and analyzing radar signals - Google Patents
Radar system and method for receiving and analyzing radar signals Download PDFInfo
- Publication number
- US11372087B2 US11372087B2 US16/382,789 US201916382789A US11372087B2 US 11372087 B2 US11372087 B2 US 11372087B2 US 201916382789 A US201916382789 A US 201916382789A US 11372087 B2 US11372087 B2 US 11372087B2
- Authority
- US
- United States
- Prior art keywords
- detected signals
- signals
- linear function
- radar
- receiving element
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
- 238000000034 method Methods 0.000 title claims description 46
- 238000012886 linear function Methods 0.000 claims description 60
- 238000012546 transfer Methods 0.000 claims description 32
- 238000004422 calculation algorithm Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 29
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 7
- 238000007906 compression Methods 0.000 description 6
- 230000006835 compression Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000013144 data compression Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/3059—Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/87—Combinations of radar systems, e.g. primary radar and secondary radar
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/9327—Sensor installation details
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/003—Transmission of data between radar, sonar or lidar systems and remote stations
Definitions
- This disclosure generally relates to a a radar system suitable for an automated vehicle and to a method for receiving and analyzing radar signals.
- Radar systems are used for many automotive applications, e.g. for advanced driver assistant systems (ADAS) comprising automatic cruise control (ACC) and/or automatic emergency breaking (AEB).
- ADAS advanced driver assistant systems
- ACC automatic cruise control
- AEB automatic emergency breaking
- Common radar sensors of such systems like front facing or side facing radar sensors, provide sensor information in terms of so-called detection lists. These lists comprise properties of physical detections performed on the data signals of the radar sensors. Typically, a detection list comprises the properties of approximately 64 to 128 physical detections.
- a single detection consists of range, angle, amplitude and velocity information of a target at which a radar signal sent by the radar system is reflected.
- CDC compressed data cube
- the three-dimensional raw data of radar sensors of a target are compressed for the CDC by applying thresholds corresponding to noise levels of the radar signals. Due to the sparse nature of the radar raw signals, a strong compression of these data is achieved by the compressed data cube. Such a compression is necessary since it is not possible to transfer an uncompressed data cube via the data transmission protocols which are currently available in automotive systems.
- the data compression within a compressed data cube is therefore based on the assumption that signals below the noise level being arbitrarily defined do not contain any relevant information. This assumption is not necessarily true since there are algorithms being able to reduce the effect of noise and to reveal information below noise level.
- object classification algorithms being based on learning or training procedures can be applied more effectively to unmodified raw signals.
- a compression based on thresholds corresponding to noise levels can introduce harmful artifacts to the transmitted signals.
- Described herein are techniques for providing a radar system and a method for receiving and analyzing radar data which provide a sufficient high transfer rate for all relevant information contained in radar raw signals and required by a special application.
- the radar system comprises at least one receiving element which is configured to detect reflected radar signals being reflected by an object in a field-of-view of the system.
- the receiving element is further configured to generate detected signals indicative of the reflected radar signals detected by the receiving element.
- an auto-encoding device performs an auto-encoding operation on the detected signals and is embedded in the receiving element. Therefore, the receiving element outputs the detected signals in an encoded form.
- the encoded form of the detected signals is preferably a lossy encoded form. This means that data being reconstructed from the encoded detected signals can differ from the original detected signals. However, the data loss due to the encoding and reconstructing of the detected signals is to be minimized, e.g. by a training procedure.
- a compact unit for receiving and encoding the reflected or raw radar signals is achieved.
- Such a compact receiving and encoding unit can be easily implemented in automotive applications and already provides encoded data without the need for an additional encoding device.
- the output of the receiving element can also be denoted as an “intermediate representation” of the detected signals. Due to the encoding of the data, the quantity of data to be transferred is generally decreased. Therefore, the information provided by the reflected radar signals can be transferred with a higher transfer rate at the output of the receiving device, i.e. in comparison to a receiving element which does not output encoded data.
- the “dimensionality” of the intermediate representation i.e. the maximum quantity of data or number of samples, can therefore be specified in accordance with the available transmission bandwidth of a respective interface which is to be used for transferring the encoded signals. In addition, no artifacts due to arbitrarily defined thresholds are introduced when encoding and transferring the detected signals.
- a compression factor can be defined as the ratio of samples of the original detected signals to the number of samples or corresponding data sets of the encoded detected signals. Therefore, the compression factor is a measure for reducing the quantity of data to be transferred or, vice versa, a measure for the enhancement of the data transfer rate at the output of the receiving element.
- the original detected signals are signals which are directly generated e.g. by antennas of the receiving element. That is, these data are regarded as raw data which have not yet been exposed to further processing steps, like one or more Fourier transforms which are typically used to create e.g. a Range-Doppler-Map.
- the system further comprises a transfer device in communication with the receiving element and a controller in communication with the transfer device.
- the transfer device transfers the encoded detected signals from the receiving element to the controller, whereas the controller comprises a decoding device which performs a decoding operation in order to decode the encoded detected signals.
- a standard transfer device like e.g. CAN-bus, can be used for the data transfer.
- a transfer device is usually available in an automotive application or an automated vehicle.
- the decoding device comprised by the controller is preferably the counterpart of the auto-encoding device since the decoding device has to reconstruct the detected signals with a minimum deviation with respect to the original detected signals.
- the auto-encoding device applies a first non-linear function to the detected signals in order to encode the detected signals
- the decoding device applies a second non-linear function for decoding the encoded detected signals.
- the first and second non-linear functions depend on each other. Therefore, the properties of the data transfer, e.g. regarding an unavoidable data loss, can be assessed and/or controlled by the properties of the non-linear functions. This can be performed, for example, by controlling parameters which the non-linear functions depend on.
- the first non-linear function is different from the second non-linear function.
- a first neural network derives parameters of the first non-linear function which is applied in the auto-encoding operation
- a second neural network derives parameters of the second non-linear function which is applied in the decoding operation.
- the first and second neural networks can be implemented on a development system which is used before installing the radar system e.g. on an automated vehicle.
- the first and second neural networks can be implemented on the controller which is part of the radar system.
- the first and second non-linear functions depend on each other, the first and second neural networks are may be connected to each other, i.e. due to the reconstruction requirement.
- convolutional neural networks are well suited for processing radar raw data. Therefore, the set of parameters for the first and second non-linear functions can be regarded as one set of parameters which are defined by the first and second neural networks.
- the controller comprises a discriminator which evaluates the parameters of the first and second non-linear functions as part of a training procedure of the auto-encoding and decoding devices.
- the task of the discriminator is therefore evaluating the parameters of the first and second non-linear functions in such a manner that the difference between the original detected signals and the reconstructed signals is minimized.
- the discriminator receives the original detected signals or raw signals during training procedure without encoding from the receiving element as well as the encoded and decoded, i.e. reconstructed, detected signals.
- the parameters of the first and second non-linear functions are varied by the first and second neural networks until the original and the reconstructed signals coincide sufficiently with each other.
- a residual deviation between the original and reconstructed signals can be defined in order to terminate the training procedure.
- the residual deviation can be defined in such a manner that the amount of data to be transferred is reduced as far as possible, or that the relevant information obtained by the data is maximized.
- the controller comprises at least one application algorithm for analyzing the detected signals, and the discriminator uses the application algorithm during the training procedure in order to evaluate the parameters for the first and second non-linear functions.
- the at least one application algorithm comprises at least one algorithm for landmark classification, pedestrian classification and/or bicycle classification.
- the results provided by the at least one application algorithm can be further processed by other automotive applications, e.g. by a advanced driver assistant system (ADAS).
- ADAS advanced driver assistant system
- the application algorithm can be used during the training procedure for the evaluation of the parameters of the first and second non-linear functions. For example, an algorithm for identifying or classifying an object can be applied on the original detected signals and on the reconstructed signals, e.g. for identifying a landmark or a pedestrian, and the training procedure will end if there is sufficient consistency regarding the identification results.
- the training procedure can be tailored and optimized with respect to the required application for which the radar signals are detected.
- the unavoidable data loss due to the auto-encoding and decoding operations can therefore be minimized with respect to the required application, e.g. identification of objects, instead of defining an arbitrary level, e.g. noise level, for restricting the quantity of data to be transferred.
- the unavoidable data loss is “transferred” to irrelevant data with respect to the required application by the training procedure.
- the training procedure is performed before installing the radar system on an automated vehicle by applying a large number of data sets, i.e. detected signals from known objects in original form as well as in encoded and decoded form.
- a training procedure can preferably be repeated in order to verify the parameters of the first and second non-linear functions.
- a training procedure can be triggered when the transfer device allows a transfer of a large quantity of data, e.g. when the vehicle is not moving.
- the receiving element comprises an embedded auto-encoding device which encodes detected signals being output by the receiving element.
- another aspect relates to a method for receiving and analyzing radar signals.
- Reflected radar signals which are reflected by an object in a field-of-view of a radar system are detected via at least one receiving element.
- the detected signals are auto-encoded via an auto-encoding device being embedded in the receiving element.
- the encoded radar signals are transferred to a controller and decoded via a decoding device which is comprised by the controller.
- the decoded radar signals are finally analyzed via at least one application algorithm comprised by the controller.
- the quantity of data to be transferred from the receiving element to the controller can be decreased. Therefore, the transfer rate for the relevant information can be increased. Furthermore, the occurrence of artifacts in reconstructed or decoded radar signals can be minimized since no arbitrary restrictions for the data, like noise levels, are used.
- FIG. 1 is a vehicle-based radar system in accordance with one embodiment
- FIG. 2 is a schematic representation of data compression and data reconstruction performed by the system of FIG. 1 ;
- FIG. 3 is a flow chart illustrating a training procedure performed for the system of FIG. 1 .
- One or more includes a function being performed by one element, a function being performed by more than one element, e.g., in a distributed fashion, several functions being performed by one element, several functions being performed by several elements, or any combination of the above.
- first, second, etc. are, in some instances, used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another.
- a first contact could be termed a second contact, and, similarly, a second contact could be termed a first contact, without departing from the scope of the various described embodiments.
- the first contact and the second contact are both contacts, but they are not the same contact.
- the term “if” is, optionally, construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context.
- the phrase “if it is determined” or “if [a stated condition or event] is detected” is, optionally, construed to mean “upon determining” or “in response to determining” or “upon detecting [the stated condition or event]” or “in response to detecting [the stated condition or event],” depending on the context.
- FIG. 1 illustrates a vehicle-based radar system, hereinafter referred to as the system 10 .
- the system 10 includes a transmit element 12 and at least one receiving element 14 comprising a plurality of antennas 16 , e.g. a first antenna 16 A and a second antenna 16 B.
- the transmit element 12 transmits a radar signal 18 which is reflected by a first object 19 A and/or a second object 19 B in a field-of-view of the system 10 as reflected radar signals 20 .
- the reflected radar signals 20 are detected by the first antenna 16 A and second antenna 16 B of the receiving element 14 in order to provide detected signals 21 indicative of the reflected radar signals 20 .
- the receiving element 14 comprises an auto-encoding device 22 .
- the auto-encoding device 22 is embedded in the receiving element 14 in order to provide a compact unit together with the antennas 16 .
- the auto-encoding device 22 performs an auto-encoding operation on the detected signals 21 by applying a first non-linear function 103 (see FIG. 3 ) to the detected signals 21 . Therefore, encoded detected signals 30 are output by the auto-encoding device 22 .
- the receiving element 14 comprising the embedded auto-encoding device 22 outputs the encoded detected signals 30 instead of the original detected signals 21 .
- the antennas 16 have a typical sampling rate of 100 to 1000 MHz with a typical resolution of 16 bit.
- One single scan of the detected signals 21 provides an input X for the auto-encoding device 22 consisting of 1000 to 10000 samples.
- the encoded detected signals 30 are obtained as a so-called intermediate representation Z comprising a much smaller quantity of data, e.g. several hundred samples only. In this example, this leads to a compression factor of approximately 10 for the detected signals 21 due to the auto-encoding.
- the system 10 further comprises a transfer device 25 in communication with the receiving element 14 and a controller 26 in communication with the transfer device 25 .
- the transfer device 25 transfers the encoded detected signals 30 from the receiver element 14 to the controller 26 .
- the controller 26 comprises a decoding device 27 , a discriminator 29 and an application algorithm 31 to be applied to the detected signals.
- the controller 26 comprises a device (not shown) for providing a transmit signal 28 to the transmit element 12 in order to generate the radar signal 18 .
- the transfer device 25 is, for example, a CAN-bus used in typical automotive systems.
- the transfer device 25 transfers the encoded detected signals 30 from the receiving element 14 to the decoding device 27 of the controller 26 .
- the decoding device 27 performs a decoding operation by applying a second non-linear function 203 (see FIG. 3 ) to the encoded detected signals 30 .
- the decoding operation performed by the decoding device 27 is illustrated on the right side of FIG. 2 .
- decoded or reconstructed signals 40 are generated as output X′ of the decoding device 27 .
- an unavoidable data loss occurs, i.e. the decoded or reconstructed signals 40 may deviate from the original detected signals 21 .
- no arbitrary restrictions e.g. thresholds corresponding to noise levels
- parameters of the non-linear functions 103 , 203 are optimized by a training procedure.
- the output X′ of the decoding device 27 i.e. the decoded signals 40
- the discriminator 29 evaluates parameters of the first and second non-linear function which are applied within the encoding and decoding steps. This evaluation is performed by transferring the original detected signals 21 to the controller 26 as well.
- the decoded signals 40 are compared to the original detected signals 21 and the parameters of the first and second non-linear functions 103 , 203 are varied until the deviation between the original detected signals 21 and the decoded signals 40 is minimized.
- the application algorithm 31 (which is generally to be applied to the detected signals 21 ) is additionally included in the evaluation step. That is, the application algorithm 31 is applied to the detected signals 21 and to the decoded signals 40 , respectively, and a comparison of the results is performed afterwards.
- the discrimination step performed by the discriminator 29 can be adapted to the application algorithm 31 being provided for the detected signals 21 .
- a comparison of original and reconstructed signals is used for evaluating and controlling the parameters of the first and second non-linear functions. Due to this, data having no or minor relevance is automatically suppressed by the discrimination.
- the evaluation of the parameters for the first and second non-linear functions 103 , 203 is performed until the deviation between the original and reconstructed signals (i.e. raw signals or application results) is minimized. In detail, the evaluation is performed via a training procedure as illustrated in FIG. 3 .
- the output of the antennas 16 i.e. the detected signals 21
- a first neural network 101 which determines parameters of the first linear function 103 performing the decoding step in order to generate the encoded detected signals 30 .
- These encoded detected signals 30 are again fed to a second neural network 201 which determines parameters of the second non-linear function 203 .
- reconstructed detected signals 301 are provided to the discriminator 29 .
- original detected signals i.e. a copy of the detected signals 21 , are also provided to the discriminator 29 .
- the result of a comparison of the reconstructed detected signals 301 and the original detected signals 303 leads to a first feedback 105 and a second feedback 205 from the discriminator 209 which is respectively used by the first and second neural networks 101 , 103 . Due to this feedback, nodes of the neural networks 101 , 201 are updated, and the parameters of the first and second functions 103 , 203 are revised. Thus, a first learning step of the training procedure is completed.
- the learning steps of the training procedure are repeated, e.g. by a further set of detected signals 21 provided for object 19 A or object 19 B, until the deviation between the original detected signals 303 and the reconstructed detected signals 301 is minimized.
- the output data of the decoding device 27 i.e. decoded signals 40 (see FIG. 2 ) is directly provided to the application algorithm 31 , i.e. after completing the training procedure for the parameters of the first and second non-linear functions 103 , 203 .
- the training procedure is performed for the first time in a testing environment, i.e. before implementing the radar system 10 e.g. in an automated vehicle. In such a testing environment, the data transfer of the original detected signals 21 , 303 can be easily performed via additional computational hardware which is typically not available in an automated vehicle.
- execution of the second mode of operation can be interrupted at a later stage, and the training procedure (e.g. using a reduced data set) can be repeated in order to verify the parameters of the first non-linear function 103 and the second non-linear function 203 .
- the transfer rate for transferring the encoded detected signals 30 from the receiving element 14 to the controller 26 is increased in comparison to a data transfer without encoding and decoding.
- the suppression of non-relevant data is performed by non-linear functions comprising parameters which are determined by a training procedure. Therefore, the unavoidable data loss due to auto-encoding and decoding via non-linear functions is automatically adapted to the required application. Therefore, no artifacts are introduced since no thresholds are arbitrarily set, e.g. corresponding to noise levels. Instead, the radar system 10 ensures that the decoded radar signals 40 or reconstructed detected signals 301 comprise maximum information required for the application algorithm used.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Electromagnetism (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Radar Systems Or Details Thereof (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims (20)
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP18173197.7A EP3570062B1 (en) | 2018-05-18 | 2018-05-18 | Radar system and method for receiving and compressing radar signals |
EP18173197.7 | 2018-05-18 | ||
EP8173197 | 2018-05-18 |
Publications (2)
Publication Number | Publication Date |
---|---|
US20190353753A1 US20190353753A1 (en) | 2019-11-21 |
US11372087B2 true US11372087B2 (en) | 2022-06-28 |
Family
ID=62217812
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/382,789 Active 2040-12-22 US11372087B2 (en) | 2018-05-18 | 2019-04-12 | Radar system and method for receiving and analyzing radar signals |
Country Status (3)
Country | Link |
---|---|
US (1) | US11372087B2 (en) |
EP (2) | EP4071497A1 (en) |
CN (1) | CN110501710B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11269058B2 (en) * | 2018-06-13 | 2022-03-08 | Metawave Corporation | Autoencoder assisted radar for target identification |
US11416077B2 (en) * | 2018-07-19 | 2022-08-16 | Infineon Technologies Ag | Gesture detection system and method using a radar sensor |
EP3767325A1 (en) * | 2019-07-19 | 2021-01-20 | Aptiv Technologies Limited | Methods and systems for processing radar reflections |
KR20210106864A (en) | 2020-02-20 | 2021-08-31 | 삼성전자주식회사 | Method and apparatus for detecting object based on radar signal |
DE102021113853A1 (en) | 2021-05-28 | 2022-12-01 | Valeo Schalter Und Sensoren Gmbh | Transmission of sensor information from an environmental sensor to a controller using a trained neural network |
US20230350056A1 (en) * | 2022-04-27 | 2023-11-02 | Infineon Technologies Ag | Radar system and method for transmitting data in a radar system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6091773A (en) * | 1997-11-12 | 2000-07-18 | Sydorenko; Mark R. | Data compression method and apparatus |
US20030169928A1 (en) * | 2002-03-08 | 2003-09-11 | Stanek Clay J. | Image compression to enhance optical correlation |
US7415162B2 (en) * | 2003-05-27 | 2008-08-19 | Zaxel Systems, Inc. | Method and apparatus for lossless data transformation with preprocessing by adaptive compression, multidimensional prediction, multi-symbol decoding enhancement enhancements |
US20150139500A1 (en) * | 2012-07-30 | 2015-05-21 | Bayerische Motoren Werke Aktiengesellschaft | Method and System for Optimizing Image Processing in Driver Assistance Systems |
US20180089505A1 (en) * | 2016-09-23 | 2018-03-29 | Samsung Electronics Co., Ltd. | System and method for deep network fusion for fast and robust object detection |
WO2018106805A1 (en) | 2016-12-09 | 2018-06-14 | William Marsh Rice University | Signal recovery via deep convolutional networks |
US20180314985A1 (en) | 2017-04-24 | 2018-11-01 | Virginia Tech Intellectual Properties, Inc. | Learning and deploying compression of radio signals |
US11189028B1 (en) * | 2020-05-15 | 2021-11-30 | Retrace Labs | AI platform for pixel spacing, distance, and volumetric predictions from dental images |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2671195B1 (en) * | 1990-12-27 | 1993-03-12 | Thomson Csf | PROCESSING A DIGITALLY CODE IMPULSE SIGNAL. |
US20070014331A1 (en) * | 2005-07-12 | 2007-01-18 | John Eldon | Ultra-wideband communications system and method |
DE102011079615A1 (en) * | 2011-07-22 | 2013-01-24 | Robert Bosch Gmbh | FMCW radar system and interference detection method for FMCW radar systems |
KR101957342B1 (en) * | 2014-04-14 | 2019-03-14 | 주식회사 만도 | Apparatus and method for velocity measurement of moving object |
US9310468B2 (en) * | 2014-05-15 | 2016-04-12 | Delphi Technologies, Inc. | Radar system with improved multi-target discrimination |
US10209344B2 (en) * | 2015-03-12 | 2019-02-19 | Src, Inc. | Methods and systems for mitigating multipath propagation |
CN107949766A (en) * | 2015-06-15 | 2018-04-20 | 修麦提克斯公司 | High-precision time-of-flight measurement system |
DE102015014750B4 (en) * | 2015-11-13 | 2021-05-12 | Audi Ag | Method for operating a motor vehicle in which an emergency call is made, and motor vehicle |
CN107607926B (en) * | 2017-10-31 | 2020-07-03 | 西安电子科技大学 | Method for detecting and processing low-traffic quasi-signal fusion target of distributed radar |
-
2018
- 2018-05-18 EP EP22176797.3A patent/EP4071497A1/en active Pending
- 2018-05-18 EP EP18173197.7A patent/EP3570062B1/en active Active
-
2019
- 2019-04-12 US US16/382,789 patent/US11372087B2/en active Active
- 2019-05-14 CN CN201910398540.2A patent/CN110501710B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6091773A (en) * | 1997-11-12 | 2000-07-18 | Sydorenko; Mark R. | Data compression method and apparatus |
US20030169928A1 (en) * | 2002-03-08 | 2003-09-11 | Stanek Clay J. | Image compression to enhance optical correlation |
US7415162B2 (en) * | 2003-05-27 | 2008-08-19 | Zaxel Systems, Inc. | Method and apparatus for lossless data transformation with preprocessing by adaptive compression, multidimensional prediction, multi-symbol decoding enhancement enhancements |
US20150139500A1 (en) * | 2012-07-30 | 2015-05-21 | Bayerische Motoren Werke Aktiengesellschaft | Method and System for Optimizing Image Processing in Driver Assistance Systems |
US20180089505A1 (en) * | 2016-09-23 | 2018-03-29 | Samsung Electronics Co., Ltd. | System and method for deep network fusion for fast and robust object detection |
WO2018106805A1 (en) | 2016-12-09 | 2018-06-14 | William Marsh Rice University | Signal recovery via deep convolutional networks |
US20180314985A1 (en) | 2017-04-24 | 2018-11-01 | Virginia Tech Intellectual Properties, Inc. | Learning and deploying compression of radio signals |
US11189028B1 (en) * | 2020-05-15 | 2021-11-30 | Retrace Labs | AI platform for pixel spacing, distance, and volumetric predictions from dental images |
Non-Patent Citations (1)
Title |
---|
Liou, et al., "Modeling word perception using the Elman network", Jul. 2008, 9 pages. |
Also Published As
Publication number | Publication date |
---|---|
CN110501710B (en) | 2023-04-18 |
CN110501710A (en) | 2019-11-26 |
EP4071497A1 (en) | 2022-10-12 |
EP3570062A1 (en) | 2019-11-20 |
EP3570062B1 (en) | 2022-06-29 |
US20190353753A1 (en) | 2019-11-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11372087B2 (en) | Radar system and method for receiving and analyzing radar signals | |
CN110741279B (en) | Method for transmitting data from an ultrasound system to a data processing device via a vehicle data bus | |
JP6411661B2 (en) | Vulnerability scanning method and apparatus | |
US20190276041A1 (en) | Apparatus and method for fault diagnosis and back-up of advanced driver assistance system sensors based on deep learning | |
US11639112B2 (en) | Fusion of data of multiple sensors for object identification | |
US20180366000A1 (en) | Method for evaluating a hazardous situation which is sensed by at least one sensor of a vehicle, method for controlling reproduction of a hazard warning and method for reproducing a hazard warning | |
US11564101B2 (en) | Method and system for handling network intrusion | |
CN117235559B (en) | Internet of things data acquisition method and system based on edge calculation | |
KR20230011117A (en) | System for anomaly detection in time series data using self-supervised learning and method thereof | |
CN114616595A (en) | Jointly training neural networks to reduce data and perform object recognition of image data | |
CN114430839A (en) | Apparatus and method for processing data of neural network | |
CN111435457A (en) | Method for classifying acquisition acquired by sensor | |
KR102549516B1 (en) | Method and device for influencing vehicle behavior | |
WO2018143278A1 (en) | Image processing device, image recognition device, image processing program, and image recognition program | |
CN115496109A (en) | Intrusion behavior analysis method and device based on intelligent automobile sensor | |
CN104287777A (en) | Ultrasonic scanning method and ultrasonic scanning system | |
US11599827B2 (en) | Method and apparatus for improving the robustness of a machine learning system | |
US20240295643A1 (en) | Method for classifying an object to be detected with at least one ultrasonic sensor | |
CN115631448B (en) | Audio and video quality inspection processing method and system | |
CN118353723B (en) | Attack detection method, device, equipment and medium | |
CN116205283B (en) | Data processing method, device, electronic equipment and computer readable storage medium | |
US20240177004A1 (en) | Method for training an artificial neural network | |
CN112291184B (en) | Intra-vehicle network intrusion detection method and terminal equipment based on neural network cluster | |
KR101958931B1 (en) | Apparatus for identifying road state using radar detection data and operating method thereof | |
CN118646879A (en) | Method for detecting compression loss of image data encoded in encoder unit |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
AS | Assignment |
Owner name: APTIV TECHNOLOGIES LIMITED, BARBADOS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:GEBHARDT, PATRIK;REEL/FRAME:053598/0395 Effective date: 20200824 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
AS | Assignment |
Owner name: APTIV TECHNOLOGIES (2) S.A R.L., LUXEMBOURG Free format text: ENTITY CONVERSION;ASSIGNOR:APTIV TECHNOLOGIES LIMITED;REEL/FRAME:066746/0001 Effective date: 20230818 Owner name: APTIV MANUFACTURING MANAGEMENT SERVICES S.A R.L., LUXEMBOURG Free format text: MERGER;ASSIGNOR:APTIV TECHNOLOGIES (2) S.A R.L.;REEL/FRAME:066566/0173 Effective date: 20231005 Owner name: APTIV TECHNOLOGIES AG, SWITZERLAND Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:APTIV MANUFACTURING MANAGEMENT SERVICES S.A R.L.;REEL/FRAME:066551/0219 Effective date: 20231006 |